Concept classification has been proven to be a useful translation method for speech-to-speech translation applications. However, preparing training data for classifier is a cumbersome task for human annotators. An unsupervised training method is introduced here that is based on utterance clustering. A technique to measure the distance between two utterances, based on the concepts they express, along with an appropriate clustering method has been adapted.
Bibliographic reference. Ettelaie, Emil / Georgiou, Panayiotis G. / Narayanan, Shrikanth S. (2008): "Towards unsupervised training of the classifier-based speech translator", In INTERSPEECH-2008, 2739-2742.